README.md

---
license: mit
datasets:
- UI-Simulator/UI-Simulator_web_data
language:
- en
base_model:
- meta-llama/Meta-Llama-3-8B-Instruct
pipeline_tag: text-generation
tags:
- agent
- web-agent
- world-model
- GUI-agent
---

# 🌍 UI-Simulator: LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training

[![License](https://img.shields.io/github/license/WadeYin9712/UI-Simulator)](LICENSE)
[![Python](https://img.shields.io/badge/python-3.8%2B-blue.svg)]()
[![Build](https://img.shields.io/badge/build-passing-brightgreen.svg)]()
[![Stars](https://img.shields.io/github/stars/WadeYin9712/UI-Simulator?style=social)]()

🔗 **Paper link**: [Link]() 

🌐 **Website**: https://ui-simulator.notion.site/llms-as-scalable-digital-world-simulator

📚 **Github:** https://github.com/WadeYin9712/UI-Simulator

📧 **Contact:** [da.yin9712@gmail.com](mailto:da.yin9712@gmail.com), [w10y20ming@gmail.com](mailto:w10y20ming@gmail.com)

---

# Model Card for Model ID

This is the Step1 agent trained with **retrieval-augmented** UI-Simulator with **UI-Simulator-Grow scaling paradigm**. It is trained to solve WebArena tasks.

## Uses

We provide a script for loading the model and run WebArena evaluation [here](https://github.com/WadeYin9712/UI-Simulator/blob/main/webarena/run.py).